© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43068
    Prev
    Next
    INDEX
    Explanations

    paleo- prefix for ancient topics

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron consistently activates on occurrences of the sequence “pale” (as in “paleontology,” “paleoclimatic,” “Paleo-…”), i.e. words or prefixes containing “pale”/“paleo.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     From
    -2.33
    StoryboardSegue
    -2.20
     We
    -2.03
     Both
    -1.95
    ⇰
    -1.93
    嘏
    -1.88
    眼下
    -1.81
    荳
    -1.81
    錞
    -1.80
    皇子
    -1.77
    POSITIVE LOGITS
    {
    2.48
    臯
    2.36
    ”
    2.14
    以前
    2.06
    蛩
    1.97
    ,“
    1.95
    魠
    1.92
    3
    1.91
    </
    1.91
    就
    1.88
    Activations Density 0.004%

    No Known Activations